US9218460B2 - Defining and mining a joint pharmacophoric space through geometric features - Google Patents
Defining and mining a joint pharmacophoric space through geometric features Download PDFInfo
- Publication number
- US9218460B2 US9218460B2 US13/466,669 US201213466669A US9218460B2 US 9218460 B2 US9218460 B2 US 9218460B2 US 201213466669 A US201213466669 A US 201213466669A US 9218460 B2 US9218460 B2 US 9218460B2
- Authority
- US
- United States
- Prior art keywords
- geometric arrangements
- geometric
- subspaces
- computer
- triangle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
-
- G06F19/705—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B15/00—ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B15/00—ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
- G16B15/30—Drug targeting using structural data; Docking or binding prediction
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
- G16B50/30—Data warehousing; Computing architectures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/40—Searching chemical structures or physicochemical data
-
- G06F19/16—
-
- G06F19/28—
-
- G06F19/707—
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Definitions
- the invention is generally related to methods for the prediction of the behavior of molecules, including the querying for compounds that have multiple or similar properties, and in particular to pharmacophore analysis and the generation and mining of pharmacophore databases for drug definition and repurposing.
- Yamanishi et al. see, e.g. Yamanishi, Y., et al. “Prediction of drug-target interaction networks from the integration of chemical and genomic spaces.” Bioinformatics 2008, 24: 232-240) develop a supervised method to infer unknown drug-target interactions by integrating chemical space and genomic space. The authors make predictions for four classes of important drug-target interactions involving enzymes, ion channels, GPCRs, and nuclear receptors. The method measures chemical similarity in the graph domain by considering the size of the largest common subgraph between two compounds. Keiser et al. (see, e.g. Keiser, M.
- Chem. Inf. Model. 2009, 49: 2190-2201 develop a technique for “target fishing” (finding all possible targets for a given compound) by analyzing the target-ligand activity matrix using Support Vector Machines (SVM) and perceptrons.
- SVM Support Vector Machines
- each chemical compound is represented by a frequency vector of topological descriptors.
- Other techniques for such prediction have used nearest-neighbors (see, e.g. Nettles, J. H. “Bridging chemical and biological space: ‘target fishing’ using 2D and 3D molecular descriptors.” J. Med. Chem. 2006, 49: 6802-6810), Bayesian models (see, e.g. Nidhi, et al.
- SAR structure-activity relationships
- a pharmacophore is a spatial arrangement of chemical features that defines a pattern essential for biological activity. Chemical features taken into account in defining pharmacophores usually include hydrogen bond donor/acceptor, charge, hydrophobicity and aromacity. The geometry of the arrangements of pharmacophores is responsible for binding between compounds and targets as well as properties of compounds such as Blood Brain Barrier (BBB) permeability (see, e.g. Zhao, Y. H., et al. “Predicting penetration across the blood-brain barrier from simple descriptors and fragmentation schemes.” J. Chem. Inf. Model. 2007, 47 : 170-175) and toxicity.
- BBB Blood Brain Barrier
- the lock-and-key model assumes that for a molecule to be active its steric characteristics should perfectly complement the shape of the receptor. What is critical to the quality of the prediction is the accuracy of the underlying binding model and the assumptions on the geometries of the binding pockets. Furthermore, if gathering information on the binding pockets is expensive in terms of time or cost, then the utility of the entire searching pipeline is hampered.
- the proposed technique answers both of these weaknesses.
- the joint pharmacophore space is a database of pharmacophores based on the geometric arrangements of pharmacophoric features of both the actives and inactives against a higher level biological goal.
- this space is directly mined to understand diversity, binding affinities, and biological properties of the actives against a particular disease.
- Our technique does not assume any knowledge on the geometries of the binding pockets or depend on any underlying binding model. Rather, these geometries are learned from the pharmacophoric space of the training set as long as the set of compounds change in a consistent way while binding to protein targets.
- the present invention discloses a technique for analyzing an entire space of pharmacophores that eliminates the need to optimize pharmacophores against a specific target.
- a computer-implemented method for generating a database of pharmacophores comprises the steps of defining a joint pharmacophore space comprising a plurality of pharmacophores, each of the plurality of pharmacophores comprising a geometric arrangement of at least three pharmacophoric features, identifying subspaces within the joint pharmacophore space, each subspace having an associated subset of the pharmacophores with similar geometric arrangements, assigning a biological activity property and a representative geometric arrangement for each subspace identified to correlate with a targeted biological activity, and storing the joint pharmacophore space, subspaces, biological activity properties, and representative geometric arrangements.
- a Joint Pharmacophore Space of chemical compounds, targets, and physicochemical/biological properties is defined using the 3-dimensional geometry of pharmacophoric features for all active and inactive molecules against multiple targets.
- the JPS is mined directly to identify pharmacophoric patterns. Identification of similar pharmacophores based on geometric arrangements allows positive/negative properties (such as BBB permeability or hERG receptor activity [see, e.g. Diller, D. J. “In Silico hERG Modeling: Challenges and Progress.” Curr. Comput .- Aided Drug Des. 2009, 5: 106-121]) to be ascribed to different subspaces. This further allows structure-based filters to be defined early in the drug discovery process.
- subspaces that show statistically significant binding activity are identified by clustering pharmacophoric features of compounds in the geometric space and identifying clusters that correlate with a certain biological activity.
- a computer-implemented method for classifying a query molecule with a database of pharmacophores comprises the steps of obtaining a database of pharmacophores, identifying at least one pharmacophoric feature for a query molecule, defining a three-dimensional coordinate for each pharmacophoric feature of the query molecule, extracting a plurality of geometric arrangements for the query molecule, comparing the plurality of geometric arrangements of the query molecule to the representative geometric arrangements in the database of pharmacophores to classify the query molecule according to its similarity with the representative geometric arrangements, and presenting the classification of the query molecule according to its similarity with the representative geometric arrangements.
- representative pharmacophoric features of the statistically significant subspaces within the JPS are used as geometric keys to convert molecules into feature vectors.
- the descriptor based on significant clusters outperforms Molprint2D, Daylight fingerprints (see, e.g. Daylight Theory Manual . Daylight Chemical Information Systems Inc.: Aliso Viejo, Calif., 2008) and 3-point pharmacophore fingerprints (see, e.g. Saeh, J. C., et al. “Lead Hopping Using SVM and 3D Pharmacophore Fingerprints.” J. Chem. Inf. Model. 2005, 45: 1122-1133) in molecular classification.
- the present invention provides a joint space of pharmacophores where the conformations of all known actives and inactives against multiple targets are considered. Such an approach allows the results from a cell-based assay to be deconvoluted into separate activity subspaces, each of which could potentially be responsible for a separate binding. These active subspaces can then be queried to find independent groups of active compounds that can be optimized independently.
- the developed system is also able to rank compounds (or compound conformations) based both on proximity to desirable subspaces and distance to undesirable subspaces and then integrate answers across multiple subspaces. Answering proximity or distance queries on a single space can be done by examining the conformations of each compound, extracting the triangles of pharmacophoric points, and measuring the rmsd between the representative cluster center and the compound triangles.
- the joint space of pharmacophores promises to be a preferred beginning investigation point for medicinal chemists.
- FIG. 1 is a diagram illustrating approach to the generation of a database of pharmacophores
- FIG. 2 is a flow chart illustrating exemplary method steps that can be used to generate the database of pharmacophores
- FIG. 4 is a diagram illustrating the extraction of local geometric features of a molecule
- FIG. 6 is an diagram presenting an illustrative example of triangle typing and grouping by type
- FIG. 7 is a diagram summarizing the process of transforming a dataset of molecules into significant clusters
- FIG. 10 is a diagram showing how the p-value may be determined from a probability density function
- FIG. 1 is a diagram illustrating an approach 100 to the generation of a database of pharmacophores.
- a joint pharmacore space 110 is generated from a biological goal 102 which may be manifested in inactive molecules 104 , active molecules 108 and targets 106 .
- Pattern matching 112 is used to identify significant pharmacophoric patterns 114 , which are used for classification 116 and top-k query 118 purposes.
- FIG. 3 is a diagram presenting exemplary steps that can be used to define the joint pharmacological space.
- a dataset is provided that comprises a plurality of molecules, wherein each molecule is identified as active or inactive towards a biological activity.
- the concept of pharmacophores is based on the kinds of interactions that take place between a set of small molecule ligands and a protein receptor.
- low-energy conformations of a molecule are generated and different pharmacophoric features of interest such as hydrogen bond donors and acceptors, aromatic rings, hydrophobic cores, and groups with positive and negative charges are extracted. While each of these features play a role in the binding activity, the exact requirement for a binding to occur typically depends on the presence of multiple such features and the inter-feature geometric distances. At the same time, it is more likely that only a part of the molecule takes active participation in the binding activity rather than the entire structure.
- the molecule illustrated in FIG. 4 contains four such triplets.
- these pharmacophoric triplets take the shape of triangles and can be thought of as the basic building blocks of any local structure that is required for a pharmacophore model. Specifically, even if the local structure for a binding consists of more than three pharmacophoric features, it can be reconstructed by joining the triplets.
- the advantages of working with triplets are computational efficiency of the ensuing analysis, and minimality, i.e., three pharmacophoric points are usually the minimum number used in pharmacophores. Similar approaches of working with pharmacophoric triplets have been studied before (Saeh, J. C.; Lyne, P.
- the triangles are then grouped into three sets or classes where, the group ⁇ Acceptor, Cation, Donor> contains two triangles while the other two groups contain one triangle each.
- the rationale behind grouping triangles into sets or classes is to keep track of triangles that are comparable to each other. More specifically, a similarity or distance between two triangles can be computed only if they are mappable to each other.
- the above feature extraction scheme provides a platform to characterize molecules using local pharmacophoric features in the geometric space.
- FIG. 7 is a diagram summarizing the process of transforming a dataset of molecules into significant clusters.
- pharmacophoric triangles were extracted from conformations of each molecule.
- a database of molecules is transformed to a database of triangles.
- all triangles in the database were grouped into sets based on their types. These groups are clustered, as shown in block 504 of FIG. 5 , and significant clusters are later identified from these clusters.
- the clustering of triangles in each group permits them to be analyzed to identify clusters that are statistically significant, thus allowing the mining geometric structures in the joint pharmacophore space and checking whether a subspace is discriminative towards a specific binding or biological activity.
- different subspaces are annotated with specific chemical/biological properties.
- the geometric arrangements in each triangle group are clustered into subspaces according to the distance between the geometric arrangements.
- the clustered subspaces are analyzed and evaluated for biologically/chemically useful properties. More specifically, if the distribution of triangles from conformations of active molecules in a cluster deviates significantly from the expected ratio, then the cluster is discriminative in nature. Thus, to identify such clusters, we develop methods to analyze the statistical significance of a cluster. Statistically significant clusters can then be applied for higher level mining tasks such as molecular classification and top-k similarity queries.
- cluster C is positive if it satisfies the following condition:
- a positive or negative biological activity property is assigned to each significant subspace, as shown in block 904 .
- a representative geometric arrangement for each significant subspace is identified, wherein the representative geometric arrangement is a geometric arrangement in the significant subspace that is most similar to the other geometric arrangements in the same significant subspace, as shown in block 906 . This can be accomplished via the kernel function described below.
- FIGS. 11 and 12 are diagrams outlining a method to classify molecules based on significant subspaces mined from the joint pharmacophore space. Given a training dataset with molecules labeled as active or inactive, we first cluster the joint pharmacophore space as described in the previous section. Next, we identify all significant triangles in this joint pharmacophore space (e.g. using k-medoid clustering) and use them as pharmacophoric keys. A triangle is a significant triangle if it forms the cluster center of a positive or negative cluster.
- all query molecules in the training dataset are converted to a feature vector where each dimension corresponds to a specific significant triangle.
- Converting a molecule to a feature vector may be accomplished as follows. Given a query molecule m, first, all triangles in m are identified. Next, each of the extracted triangles is compared to the significant triangles to identify the closest significant triangle. If the root mean square distance of the closest significant triangle is within a user-specified threshold, then the dimension corresponding to the significant triangle is incremented. Essentially, for each triangle in the query molecule, we check whether it aligns well with any of the significant triangles.
- the information is stored in the vector representation of the molecule.
- the vector representation of the query molecule is returned.
- SVM support vector machines
- One key issue that affects the performance of SVM is the choice of kernel.
- the kernel function computes the similarity between two input vectors. Theoretically, any kernel can be used as long as the similarity matrix computed by the kernel function satisfies the Mercer's conditions (Swamidass, S. J.; Chen, J.; Bruand, J.; Phung, P.; Ralaivola, L.;
- K ⁇ ( X , Y ) ⁇ i ⁇ min ⁇ ( x i , y i ) ⁇ i ⁇ max ⁇ ( x i , y i ) ⁇ ⁇ i ( 6 )
- MinMax kernel function is similar to the Tanimoto coefficient, which has been extensively used in the chemoinformatics community (see Bajorath, J., “Integration of virtual and high-throughput screening,” Nat. Rev. Drug. Discovery, 2002, 1, 882-894; Bohm, H.-J., Schneider, G., “Virtual Screening for Bioactive Molecules,” John Wiley & Sons, Inc.: New York, N.Y., USA, 2000; Whittle, M., Gillet, V. J., Willett, P., Alex, A, Loesel, J., “Enhancing the effectiveness of virtual screening by fusing nearest neighbor lists: a comparison of similarity coefficients,” J. Chem. Inf. Comput.
- FIG. 12 is a diagram presenting illustrative method steps that can be used to classify a query molecule with a database of pharmacophores.
- database of pharmacophores is obtained.
- at least one pharmacophoric measure is identified for a query molecule.
- a three-dimensional coordinate for each phramacophoric feature of the query molecule is defined.
- a plurality of geometric arrangements is extracted for the query molecule.
- a plurality of geometric arrangements of the query molecule is compared to the representative geometric arrangements in the database of pharmacophores to classify the query molecule according to its similarity with the representative geometric arrangements.
- the classification of the query molecule is presented according to its similarity with the representative geometric arrangements.
- a drug can be ‘repurposed’ if it binds to a secondary target that is also known to cure a certain disease; in other words, a drug that can cure multiple diseases. Drug repurposing allows us to bypass the entire lead optimization step and thereby lowering the risk and cost of drug discovery and development.
- a cluster is statistically significant if it is over-populated with triangles from drugs corresponding to a single disease. Such a subspace indicates the geometry required for a molecule to be active against the corresponding disease. Based on this analysis, statistically significant clusters can first be extracted and then tagged with the disease that it corresponds to. From this tagged list, an activity profile can be generated for each disease that contains all the required geometries for a molecule to be active. The activity profile can then be leveraged to identify drugs that can be repurposed. More specifically, if a drug satisfies the activity profiles of multiple diseases then it is predicted as a candidate that can be repurposed.
- embodiments of the invention may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof.
- article of manufacture (or alternatively, “computer program product”) as used herein is intended to encompass logic and/or data accessible from any computer-readable device, carrier, or media.
Abstract
Description
Further, define a cluster as a positive cluster if the ratio of triangles from conformations of active molecules (active triangle) is significantly more than the expected ratio. Mathematically, cluster C is positive if it satisfies the following condition:
where δ is a user-defined threshold parameter.
where r is the expected ratio computed using
Claims (28)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/466,669 US9218460B2 (en) | 2011-05-09 | 2012-05-08 | Defining and mining a joint pharmacophoric space through geometric features |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201161483907P | 2011-05-09 | 2011-05-09 | |
US13/466,669 US9218460B2 (en) | 2011-05-09 | 2012-05-08 | Defining and mining a joint pharmacophoric space through geometric features |
Publications (2)
Publication Number | Publication Date |
---|---|
US20120290624A1 US20120290624A1 (en) | 2012-11-15 |
US9218460B2 true US9218460B2 (en) | 2015-12-22 |
Family
ID=47142619
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/466,669 Active 2034-06-16 US9218460B2 (en) | 2011-05-09 | 2012-05-08 | Defining and mining a joint pharmacophoric space through geometric features |
Country Status (1)
Country | Link |
---|---|
US (1) | US9218460B2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10515715B1 (en) | 2019-06-25 | 2019-12-24 | Colgate-Palmolive Company | Systems and methods for evaluating compositions |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015013367A1 (en) * | 2013-07-23 | 2015-01-29 | The Research Foundation Of The City University Of New York | Method of identifying new uses of known drugs |
US20150371009A1 (en) * | 2014-06-19 | 2015-12-24 | Jake Yue Chen | Drug identification models and methods of using the same to identify compounds to treat disease |
EP3766073A4 (en) * | 2018-03-16 | 2021-12-15 | Psomagen, Inc. | Method and system for characterization of metabolism-associated conditions, including diagnostics and therapies, based on bioinformatics approach |
EP3712897A1 (en) * | 2019-03-22 | 2020-09-23 | Tata Consultancy Services Limited | Automated prediction of biological response of chemical compounds based on chemical information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020099526A1 (en) * | 1996-01-26 | 2002-07-25 | Patterson David E. | Further method of creating and rapidly searching a virtual library of potential molecules using validated molecular structural descriptors |
US7188055B2 (en) * | 1996-11-04 | 2007-03-06 | Johnson & Johnson Pharmaceutical Research, & Development, L.L.C. | Method, system, and computer program for displaying chemical data |
US20110237458A1 (en) * | 2002-07-24 | 2011-09-29 | Keddem Bioscience Ltd. | Drug discovery method |
-
2012
- 2012-05-08 US US13/466,669 patent/US9218460B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020099526A1 (en) * | 1996-01-26 | 2002-07-25 | Patterson David E. | Further method of creating and rapidly searching a virtual library of potential molecules using validated molecular structural descriptors |
US7188055B2 (en) * | 1996-11-04 | 2007-03-06 | Johnson & Johnson Pharmaceutical Research, & Development, L.L.C. | Method, system, and computer program for displaying chemical data |
US20110237458A1 (en) * | 2002-07-24 | 2011-09-29 | Keddem Bioscience Ltd. | Drug discovery method |
Non-Patent Citations (9)
Title |
---|
Bender et al. (J. Chem. Inf. Comput. Sci. (2004) vol. 44:1708-18). * |
Dixon et al. (J. Comput. Aided Mol. Des. (2006) vol. 20:647-71). * |
Koutsoukas et al. (Journal of Proteomics (2011) vol. 74:2554-74). * |
Matter et al. (J. Chem. Inf. Comput. Sci. (1999) vol. 39, No. 6:1211-1225). * |
McGregor et al., "Pharmacophore Fingerprinting. 1. Application to QSAR and Focused Library Design". Journal of Chem. Inf. Comput. Sci., vol. 39, (1999), pp. 569-574. |
Puigjane et al. (Comb. Chem. And High Throughput Screen. (2008) vol. 11:669-676). * |
Saeh et al., "Lead Hopping Using SVM and 3D Pharmacophore Fingerprints". Journal of Chem. Inf. Model., vol. 45, (2005), pp. 1122-1133. |
Wolber et al. (Drug Discovery Today (2008) vol. 13:23-29). * |
Yang (Drug Discovery Today (2010) vol. 15:444-450). * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10515715B1 (en) | 2019-06-25 | 2019-12-24 | Colgate-Palmolive Company | Systems and methods for evaluating compositions |
US10839941B1 (en) | 2019-06-25 | 2020-11-17 | Colgate-Palmolive Company | Systems and methods for evaluating compositions |
US10839942B1 (en) | 2019-06-25 | 2020-11-17 | Colgate-Palmolive Company | Systems and methods for preparing a product |
US10861588B1 (en) | 2019-06-25 | 2020-12-08 | Colgate-Palmolive Company | Systems and methods for preparing compositions |
US11315663B2 (en) | 2019-06-25 | 2022-04-26 | Colgate-Palmolive Company | Systems and methods for producing personal care products |
US11342049B2 (en) | 2019-06-25 | 2022-05-24 | Colgate-Palmolive Company | Systems and methods for preparing a product |
US11728012B2 (en) | 2019-06-25 | 2023-08-15 | Colgate-Palmolive Company | Systems and methods for preparing a product |
Also Published As
Publication number | Publication date |
---|---|
US20120290624A1 (en) | 2012-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ekins et al. | In silico pharmacology for drug discovery: methods for virtual ligand screening and profiling | |
Mousavian et al. | Drug–target interaction prediction from PSSM based evolutionary information | |
Jenkins et al. | In silico target fishing: Predicting biological targets from chemical structure | |
Aittokallio et al. | Graph-based methods for analysing networks in cell biology | |
Ehrlich et al. | Maximum common subgraph isomorphism algorithms and their applications in molecular science: a review | |
Helal et al. | Public domain HTS fingerprints: design and evaluation of compound bioactivity profiles from PubChem’s bioassay repository | |
Bunin et al. | Chemoinformatics theory | |
US20020087275A1 (en) | Visualization and manipulation of biomolecular relationships using graph operators | |
Lin et al. | Clustering methods in protein-protein interaction network | |
JPWO2007139037A1 (en) | Predict protein-compound interactions and rational design of compound libraries based on chemical genome information | |
US9218460B2 (en) | Defining and mining a joint pharmacophoric space through geometric features | |
García-Sosa et al. | DrugLogit: logistic discrimination between drugs and nondrugs including disease-specificity by assigning probabilities based on molecular properties | |
Awale et al. | Similarity mapplet: interactive visualization of the directory of useful decoys and chembl in high dimensional chemical spaces | |
A Theofilatos et al. | Computational approaches for the prediction of protein-protein interactions: a survey | |
Ranu et al. | Novel method for pharmacophore analysis by examining the joint pharmacophore space | |
Rapicavoli et al. | Computational methods for drug repurposing | |
Ji et al. | Comprehensive assessment of nine target prediction web services: which should we choose for target fishing? | |
Rohrer et al. | Impact of benchmark data set topology on the validation of virtual screening methods: exploration and quantification by spatial statistics | |
Khanna et al. | Molecular similarity and diversity approaches in chemoinformatics | |
Ning et al. | In silico structure‐activity‐relationship (SAR) models from machine learning: a review | |
Root et al. | Global analysis of large-scale chemical and biological experiments | |
Ihmels et al. | Challenges and prospects in the analysis of large-scale gene expression data | |
Galeano et al. | Drug targets prediction using chemical similarity | |
Sukumar et al. | Bio-and Chem-Informatics: where do the twain meet | |
Berenger et al. | 3D-sensitive encoding of pharmacophore features |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, CALIF Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SINGH, AMBUJ K.;RANU, SAYAN;REEL/FRAME:028176/0062 Effective date: 20120503 |
|
AS | Assignment |
Owner name: NATIONAL SCIENCE FOUNDATION, VIRGINIA Free format text: CONFIRMATORY LICENSE;ASSIGNOR:UNIVERSITY OF CALIFORNIA SANTA BARBARA;REEL/FRAME:028448/0698 Effective date: 20120620 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YR, SMALL ENTITY (ORIGINAL EVENT CODE: M2551); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY Year of fee payment: 4 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YR, SMALL ENTITY (ORIGINAL EVENT CODE: M2552); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY Year of fee payment: 8 |